A dynamic account attribute management method and system based on business changes

Abstract

The present invention relates to the field of financial technology, and discloses a dynamic account attribute management method and system based on business changes, including: collecting transaction behavior feature data during the ith business transaction; inputting the transaction behavior feature data into a transaction risk assessment model to obtain a transaction risk coefficient when a virtual account operates the ith business transaction; calculating the cumulative risk coefficient of the ith business transaction, inputting the cumulative risk coefficient, an initial credit score and a transaction risk coefficient into the credit assessment model to obtain a variable credit score of the virtual account, and determining a first target authority level to which the virtual account belongs according to the variable credit score; performing transaction selection for the ith business transaction according to the first target authority level, and assigning and updating the initial credit score according to the variable credit score; the present invention is conducive to timely responding to business changes, and further conducive to providing sufficient transaction security protection when the business changes.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and more specifically, to a method and system for dynamic account attribute management based on business changes. Background Art

[0002] In the real estate industry, virtual account management systems play a key role in various business application scenarios, such as housing security, pre-sale and maintenance fund management; these scenarios require handling a large number of complex and changeable fund management tasks; traditional account management methods often seem unable to cope with these needs; for example, fund management at multiple levels such as communities, buildings, units and houses, including pre-sale fund management during the transaction process, deposit management, community public revenue management in property management, preparatory fund management in property management committee management, elevator fire special fund management, prepaid fund accounts and house maintenance fund accounts, etc., all require highly sophisticated and dynamically adjusted permission management systems.

[0003] At present, most of the existing account authority management is implemented based on fixed rules and manual adjustment, which cannot adapt to the dynamic adjustment and changes of business. Although there are some related improvement documents, for example, the patent with publication number CN117196809A discloses an operation authority control method, device and server based on account level, which realizes dynamic control of account operation authority through the correspondence between account level and operation authority; however, through research and practical application of the above method and prior art, it is found that the above method and prior art have at least the following defects:

[0004] (1) It is impossible to determine the transaction risk coefficient in real time based on the transaction behavior characteristic data, and thus it is impossible to adjust the credit score of the virtual account based on the transaction risk coefficient. Furthermore, it is impossible to determine the current authority level of the virtual account based on the updated credit score;

[0005] (2) When faced with a dynamically changing trading environment and diverse fund management needs, it is impossible to respond to business changes in a timely manner through authority level comparison, and thus is unable to provide sufficient transaction security protection when the business (amount) changes. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for dynamic account attribute management based on business changes.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A dynamic account attribute management method based on business changes, the method comprising:

[0009] Obtaining the initial credit score of the virtual account, recording the i-th business transaction of the virtual account, and collecting transaction behavior feature data when the user operates the i-th business transaction through the virtual account, where i is an integer greater than zero;

[0010] Input the transaction behavior feature data into the pre-trained transaction risk assessment model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction;

[0011] Calculate the cumulative risk coefficient of the i-th business transaction, input the cumulative risk coefficient, the initial credit score and the transaction risk coefficient into the pre-built credit assessment model to obtain the variable credit score of the virtual account, and determine the first target authority level of the virtual account when executing the i-th business transaction according to the variable credit score;

[0012] According to the first target authority level of the virtual account at the current moment, a transaction selection is performed for the i-th business transaction, and the initial credit score is assigned and updated according to the changed credit score; the transaction selection includes one of allowing execution or prohibiting execution.

[0013] Furthermore, the transaction behavior characteristic data includes multiple transaction behavior characteristic items, and the transaction behavior characteristic items include the transaction amount of the i-th business transaction, the ratio of the transaction amount to the account balance, the ratio of the average transaction time interval to the transaction time interval, the transaction period and the transaction location.

[0014] Furthermore, the training logic of the transaction risk assessment model is as follows:

[0015] Acquire historical transaction risk training data, and divide the historical transaction risk training data into a transaction risk training set and a transaction risk test set, wherein the historical transaction risk training data includes transaction behavior feature data and its corresponding transaction risk coefficient;

[0016] Construct a regression network, use the transaction behavior feature data in the transaction risk training set as the input data of the regression network, and use the transaction risk coefficient in the transaction risk training set as the output data of the regression network, train the regression network, and obtain an initial transaction risk assessment network;

[0017] The initial transaction risk assessment network is model verified using the transaction risk test set, and the output of the initial transaction risk assessment network that is less than or equal to the preset test error threshold is used as the trained transaction risk assessment model.

[0018] Furthermore, the generation logic of the transaction risk coefficient is as follows:

[0019] Extracting the trading period and trading location from multiple trading behavior feature items;

[0020] Input trading sessions into predefined time ratio quantization functions and inputting the transaction location into the predefined location ratio quantification function In the above equation, we get the time ratio and location ratio;

[0021] Wherein, the predefined time ratio quantization function The function expression is:

[0022] ;

[0023] Where: Indicates the trading session. Indicates the working transaction time interval;

[0024] Wherein, the predefined location ratio quantization function The function expression is:

[0025] ;

[0026] Where: Indicates the place of transaction. Indicates a collection of commonly used locations;

[0027] The time ratio is replaced with the trading period in the trading behavior feature item, and the location ratio is replaced with the trading location in the trading behavior feature item to obtain an updated trading behavior feature item;

[0028] Input the updated transaction behavior feature item into the pre-built mathematical calculation model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction;

[0029] The mathematical expression of the mathematical calculation model is as follows:

[0030] ;

[0031] Where: is the transaction risk coefficient of the i-th business transaction, is the weight factor of the jth transaction behavior feature item, The eigenvalue of the jth transaction behavior feature item, is the mean value of the j-th transaction behavior feature item, is the standard deviation of the j-th transaction behavior characteristic item, is an exponential function, is the total number of transaction behavior feature items.

[0032] Further, the calculation of the cumulative risk coefficient of the i-th business transaction includes:

[0033] Retrieve the transaction risk coefficient of each business transaction;

[0034] The cumulative risk coefficient is calculated by formulating the transaction risk coefficient of each business transaction; the calculation formula is: ; Where: is the cumulative risk factor, The total number of business transactions.

[0035] Furthermore, the model expression of the pre-built credit assessment model is as follows:

[0036] ;

[0037] Where: To change your credit score, is the initial credit score, is the credit score correction factor, is a logarithmic function, is the inverse tangent function, and (a, b) is the preset risk coefficient interval.

[0038] Furthermore, the determining of the first target authority level to which the virtual account belongs when executing the i-th business transaction includes:

[0039] Retrieving pre-stored credit score intervals; the credit score intervals include a first credit score interval, a second credit score interval, and a third credit score interval;

[0040] The changed credit score is compared with the credit score interval, the credit score interval to which the changed credit score belongs is taken as the target credit score interval, and based on the mapping relationship between the credit score interval and the authority level, the first target authority level to which the virtual account belongs when executing the i-th business transaction is obtained.

[0041] Further, the selecting a transaction for the i-th business transaction includes:

[0042] Extract the amount range to which the transaction amount of the i-th business transaction belongs, and according to the preset relationship between the amount range and the authority level, use the authority level associated with the amount range as the second target authority level;

[0043] Comparing the first target permission level and the first target permission level being higher than the second target permission level;

[0044] If the first target permission level is higher than the second target permission level, or the first target permission level is the same as the second target permission level, the operation of the i-th business transaction is allowed to be performed;

[0045] If the first target authority level is lower than the second target authority level, the operation of the i-th business transaction is prohibited.

[0046] A dynamic account attribute management system based on business changes, comprising:

[0047] A data acquisition module is used to obtain the initial credit score of the virtual account, record the i-th business transaction of the virtual account, and collect transaction behavior feature data when the user operates the i-th business transaction through the virtual account, where i is an integer greater than zero;

[0048] The risk regression module is used to input the transaction behavior feature data into the pre-trained transaction risk assessment model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction;

[0049] A level determination module is used to calculate the cumulative risk coefficient of the i-th business transaction, input the cumulative risk coefficient, the initial credit score and the transaction risk coefficient into a pre-built credit assessment model to obtain the variable credit score of the virtual account, and determine the first target authority level of the virtual account when executing the i-th business transaction according to the variable credit score;

[0050] The transaction selection module is used to select a transaction for the i-th business transaction according to the first target authority level of the virtual account at the current moment, and to assign and update the initial credit score according to the changed credit score; the transaction selection includes one of allowing execution or prohibiting execution.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present application discloses a dynamic account attribute management method and system based on business changes, including: collecting transaction behavior feature data during the ith business transaction; inputting the transaction behavior feature data into a transaction risk assessment model to obtain a transaction risk coefficient when a virtual account operates the ith business transaction; calculating the cumulative risk coefficient of the ith business transaction, inputting the cumulative risk coefficient, the initial credit score and the transaction risk coefficient into the credit assessment model to obtain the variable credit score of the virtual account, and determining the first target authority level to which the virtual account belongs according to the variable credit score; performing transaction selection for the ith business transaction according to the first target authority level, and assigning and updating the initial credit score according to the variable credit score; based on the above content, the present invention can respond to business changes in a timely manner through authority level comparison when facing a dynamically changing transaction environment and diversified fund management needs, thereby facilitating sufficient transaction security protection when the business (amount) changes; in addition, by determining the transaction risk coefficient in real time according to the transaction behavior feature data, and adjusting the credit score of the virtual account according to the transaction risk coefficient, it is facilitating the determination of the current authority level of the virtual account through the updated credit score, and further facilitating the provision of important decision support for transaction selection when responding to business changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flowchart of a dynamic account attribute management method based on business changes provided by the present invention;

[0054] Figure 2 A schematic diagram of the module structure of a dynamic account attribute management system based on business changes provided by the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example 1

[0057] See also Figure 1 As shown, this embodiment discloses a method for dynamic account attribute management based on business changes, the method comprising:

[0058] S101: Obtaining an initial credit score of a virtual account, recording the i-th business transaction of the virtual account, and collecting transaction behavior characteristic data when a user performs the i-th business transaction through the virtual account, where i is an integer greater than zero;

[0059] It should be understood that: when each virtual account completes registration, the system will assign an initial credit score to the virtual account; and when each virtual account completes registration, the initial credit score assigned can be consistent (such as the initial credit score is 100) or inconsistent, which is specifically determined according to the virtual account review mechanism preset during registration. The virtual account review mechanism is not the focus of the description of the present invention, and it does not affect the feasibility of the specific implementation of the present invention. Therefore, no excessive introduction and elaboration will be made here;

[0060] Specifically, the transaction behavior characteristic data includes a plurality of transaction behavior characteristic items, including but not limited to the transaction amount of the i-th business transaction, the ratio of the transaction amount to the account balance, the ratio of the average transaction time interval to the transaction time interval, the transaction period and the transaction location, etc.;

[0061] It should be noted that: the transaction behavior characteristic data is collected in real time through a pre-deployed system monitoring program, that is, the transaction interface information in each business transaction process is monitored in real time through the system monitoring program to obtain the transaction behavior characteristic data; wherein, the transaction amount to account balance ratio refers to the ratio between the transaction amount of the ith business transaction and the account balance, and the average transaction time interval to transaction time interval ratio refers to the ratio between the average transaction time interval and the transaction time of the ith business transaction and the time interval of the previous business transaction, that is, ;

[0062] S102: Inputting the transaction behavior feature data into a pre-trained transaction risk assessment model to obtain a transaction risk coefficient when the virtual account operates the i-th business transaction;

[0063] Specifically, the training logic of the transaction risk assessment model is as follows:

[0064] Acquire historical transaction risk training data, and divide the historical transaction risk training data into a transaction risk training set and a transaction risk test set, wherein the historical transaction risk training data includes transaction behavior feature data and its corresponding transaction risk coefficient;

[0065] It should be noted that: the transaction behavior characteristic data in the historical transaction risk training data is collected and recorded by the system monitoring program and pre-stored in the system database;

[0066] The generation logic of the transaction risk coefficient is as follows:

[0067] Extracting the trading period and trading location from multiple trading behavior feature items;

[0068] Input trading sessions into predefined time ratio quantization functions and inputting the transaction location into the predefined location ratio quantification function In the above equation, we get the time ratio and location ratio;

[0069] Wherein, the predefined time ratio quantization function The function expression is:

[0070] ;

[0071] Where: Indicates the trading session. Indicates the working transaction time interval;

[0072] It should be noted that the working transaction time interval is manually set and determined by the technical staff in advance;

[0073] Wherein, the predefined location ratio quantization function The function expression is:

[0074] ;

[0075] Where: Indicates the place of transaction. Indicates a collection of commonly used locations;

[0076] It should be noted that: the transaction location refers to the area where the virtual account is located when logging into the terminal, and the common location set refers to the common recording area of ​​the virtual account when logging into the terminal; the common recording area is determined according to the login frequency; a further example is that, assuming that the login frequency threshold is set to 5, if the recording area of ​​the virtual account when logging into the terminal includes Z1 and Z2, if the login frequency of Z1 is 6 and the login frequency of Z2 is 3, then Z1 is used as the common recording area, and Z2 is the uncommon recording area;

[0077] The time ratio is replaced with the trading period in the trading behavior feature item, and the location ratio is replaced with the trading location in the trading behavior feature item to obtain an updated trading behavior feature item;

[0078] Input the updated transaction behavior feature item into the pre-built mathematical calculation model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction;

[0079] The mathematical expression of the mathematical calculation model is as follows:

[0080] ;

[0081] Where: is the transaction risk coefficient of the i-th business transaction, is the weight factor of the jth transaction behavior feature item, is the characteristic value of the jth transaction behavior characteristic item, is the mean value of the j-th transaction behavior feature item, is the standard deviation of the j-th transaction behavior characteristic item, is an exponential function, is the total number of transaction behavior feature items;

[0082] It should be noted that the mean value of the j-th transaction behavior characteristic item and the standard deviation of the j-th transaction behavior characteristic item are determined by calculating the mean value and the standard deviation of the corresponding transaction behavior characteristic items in multiple historical business transactions;

[0083] Construct a regression network, use the transaction behavior feature data in the transaction risk training set as the input data of the regression network, and use the transaction risk coefficient in the transaction risk training set as the output data of the regression network, train the regression network, and obtain an initial transaction risk assessment network;

[0084] The initial transaction risk assessment network is validated using the transaction risk test set, and the initial transaction risk assessment network with a value less than or equal to a preset test error threshold is output as a trained transaction risk assessment model;

[0085] It should be noted that the regression network is a specific one of regression algorithm models such as random forest, decision tree, support vector machine, polynomial regression, linear regression or neural network.

[0086] S103: Calculate the cumulative risk coefficient of the i-th business transaction, input the cumulative risk coefficient, the initial credit score and the transaction risk coefficient into a pre-built credit assessment model to obtain the variable credit score of the virtual account, and determine the first target authority level of the virtual account when executing the i-th business transaction according to the variable credit score;

[0087] In implementation, the calculation of the cumulative risk coefficient of the i-th business transaction includes:

[0088] Retrieve the transaction risk coefficient of each business transaction;

[0089] It should be noted that the transaction risk factor of each business transaction is pre-stored in the system database;

[0090] The cumulative risk coefficient is calculated by formulating the transaction risk coefficient of each business transaction; the calculation formula is: ; Where: is the cumulative risk factor, is the total number of business transactions;

[0091] Specifically, the model expression of the pre-built credit assessment model is as follows:

[0092] ;

[0093] Where: To change your credit score, is the initial credit score, is the credit score correction factor, is a logarithmic function, is the inverse tangent function, (a, b) is the preset risk coefficient interval;

[0094] It should be understood that the risk coefficient interval is set in advance by the technicians based on the experimental data. , it means that the i-th business transaction is at a low risk level or in a risk-free state; when , it means that the i-th business transaction is at a medium risk level; and when , it means that the i-th business transaction is at a high risk level;

[0095] By combining the risk coefficient of each transaction with the cumulative risk coefficient, the present invention takes into account the impact of single transaction behavior and long-term transaction behavior on the credibility of the virtual account, which is conducive to making the calculated variable credit score of the virtual account objective and authentic;

[0096] In implementation, determining the first target permission level to which the virtual account belongs when executing the i-th business transaction includes:

[0097] Retrieving pre-stored credit score intervals; the credit score intervals include a first credit score interval, a second credit score interval, and a third credit score interval;

[0098] It should be noted that: the minimum value of the first credit score interval is greater than the maximum value of the second credit score interval, and the minimum value of the second credit score interval is greater than the maximum value of the third credit score interval;

[0099] Compare the changed credit score with the credit score interval, take the credit score interval to which the changed credit score belongs as the target credit score interval, and obtain the first target authority level to which the virtual account belongs when executing the i-th business transaction according to the mapping relationship between the credit score interval and the authority level;

[0100] It should be noted that: when comparing the changed credit score with the credit score interval, if the changed credit score falls into any of the first credit score interval, the second credit score interval and the third credit score interval, the corresponding credit score interval will be used as the target credit score interval;

[0101] It should also be noted that: multiple mapping relationships between credit score intervals and authority levels are pre-stored in the system database, and in each mapping relationship, there is a credit score interval and an associated authority level; each credit score interval and the associated authority level are manually associated and bound by technical personnel to form a mapping relationship; wherein, the authority levels include authority level A, authority level B and authority level C, the authority level A is higher than authority level B, and the authority level B is higher than authority level C, the higher the authority level, the more secure the corresponding virtual account, and the fewer transaction restrictions granted, and the greater the transaction authority.

[0102] S104: According to the first target authority level to which the virtual account currently belongs, a transaction selection is performed for the i-th business transaction, and the initial credit score is assigned and updated according to the changed credit score; the transaction selection includes one of allowing execution or prohibiting execution;

[0103] In implementation, the transaction selection for the i-th business transaction includes:

[0104] Extract the amount range to which the transaction amount of the i-th business transaction belongs, and according to the preset relationship between the amount range and the authority level, use the authority level associated with the amount range as the second target authority level;

[0105] It should be noted that: a plurality of preset relationships between amount intervals and authority levels are pre-stored in the system database, and in each preset relationship, there is an amount interval and an authority level associated and bound thereto; each amount interval and the authority level associated and bound thereto are manually associated and bound by a technician to form a preset relationship; similarly, the number of the amount intervals and the range of each amount interval are also manually set in advance by the technician;

[0106] Comparing the first target permission level and the first target permission level being higher than the second target permission level;

[0107] If the first target permission level is higher than the second target permission level, or the first target permission level is the same as the second target permission level, the operation of the i-th business transaction is allowed to be performed;

[0108] If the first target authority level is lower than the second target authority level, the operation of the i-th business transaction is prohibited;

[0109] For example, assuming that the transaction amount of the i-th business transaction is RMB 100,000, and the second target authority level associated with the amount range to which the transaction amount belongs is authority level B, and assuming that the first target authority level is authority level A, according to the above description, authority level A is higher than authority level B, therefore, the first target authority level is higher than the second target authority level, and the operation of the i-th business transaction is allowed to be executed; on the contrary, if the second target authority level is authority level A, and the first target authority level is authority level B, since authority level A is higher than authority level B, therefore, the first target authority level is lower than the second target authority level, the operation of the i-th business transaction is prohibited to be executed;

[0110] It should also be noted that: after completing the transaction selection for each business transaction, the changed credit score needs to be assigned to the initial credit score to achieve dynamic update of the initial credit score, which is conducive to ensuring the dynamicity and reliability of the credit score;

[0111] By performing real-time credit score updates, obtaining a first target authority level based on the updated credit score, and then comparing the first target authority level with the second target authority level, the present invention can respond to business changes in a timely manner when faced with dynamically changing transaction environments and diverse fund management needs, thereby facilitating the provision of adequate transaction security protection when the business (amount) changes.

[0112] Example 2

[0113] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a dynamic account attribute management system based on business changes. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes:

[0114] The data acquisition module 210 is used to obtain the initial credit score of the virtual account, record the i-th business transaction of the virtual account, and collect transaction behavior characteristic data when the user operates the i-th business transaction through the virtual account, where i is an integer greater than zero;

[0115] The risk regression module 220 is used to input the transaction behavior feature data into a pre-trained transaction risk assessment model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction;

[0116] The level determination module 230 is used to calculate the cumulative risk coefficient of the i-th business transaction, input the cumulative risk coefficient, the initial credit score and the transaction risk coefficient into a pre-built credit assessment model to obtain the variable credit score of the virtual account, and determine the first target authority level of the virtual account when executing the i-th business transaction according to the variable credit score;

[0117] The transaction selection module 240 is used to select a transaction for the i-th business transaction according to the first target authority level of the virtual account at the current moment, and to assign and update the initial credit score according to the changed credit score; the transaction selection includes one of allowing execution or prohibiting execution.

[0118] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0119] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0125] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0126] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A dynamic account attribute management method based on business changes, characterized in that: The method comprises: Obtaining the initial credit score of the virtual account, recording the i-th business transaction of the virtual account, and collecting transaction behavior feature data when the user operates the i-th business transaction through the virtual account, where i is an integer greater than zero; Input the transaction behavior feature data into the pre-trained transaction risk assessment model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction; Calculate the cumulative risk coefficient of the i-th business transaction, input the cumulative risk coefficient, the initial credit score and the transaction risk coefficient into the pre-built credit assessment model to obtain the variable credit score of the virtual account, and determine the first target authority level of the virtual account when executing the i-th business transaction according to the variable credit score; According to the first target authority level of the virtual account at the current moment, a transaction selection is performed for the i-th business transaction, and the initial credit score is assigned and updated according to the changed credit score; the transaction selection includes one of allowing execution or prohibiting execution.

2. The method for dynamic account attribute management based on business changes according to claim 1, characterized in that: The transaction behavior characteristic data includes multiple transaction behavior characteristic items, and the transaction behavior characteristic items include the transaction amount of the i-th business transaction, the ratio of the transaction amount to the account balance, the ratio of the average transaction time interval to the transaction time interval, the transaction period and the transaction location.

3. The method for dynamic account attribute management based on business changes according to claim 2, characterized in that: The training logic of the transaction risk assessment model is as follows: Acquire historical transaction risk training data, and divide the historical transaction risk training data into a transaction risk training set and a transaction risk test set, wherein the historical transaction risk training data includes transaction behavior feature data and its corresponding transaction risk coefficient; Construct a regression network, use the transaction behavior feature data in the transaction risk training set as the input data of the regression network, and use the transaction risk coefficient in the transaction risk training set as the output data of the regression network, train the regression network, and obtain an initial transaction risk assessment network; The initial transaction risk assessment network is model verified using the transaction risk test set, and the output of the initial transaction risk assessment network that is less than or equal to the preset test error threshold is used as the trained transaction risk assessment model.

4. The method for dynamic account attribute management based on business changes according to claim 3, characterized in that: The generation logic of the transaction risk coefficient is as follows: Extracting the trading period and trading location from multiple trading behavior feature items; Input trading sessions into predefined time ratio quantization functions and inputting the transaction location into the predefined location ratio quantification function In the above equation, we get the time ratio and location ratio; Wherein, the predefined time ratio quantization function The function expression is: ; Where: Indicates the trading session. Indicates the working transaction time interval; Wherein, the predefined location ratio quantization function The function expression is: ; Where: Indicates the place of transaction. Indicates a collection of commonly used locations; The time ratio is replaced with the trading period in the trading behavior feature item, and the location ratio is replaced with the trading location in the trading behavior feature item to obtain an updated trading behavior feature item; Input the updated transaction behavior feature item into the pre-built mathematical calculation model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction; The mathematical expression of the mathematical calculation model is as follows: ; Where: is the transaction risk coefficient of the i-th business transaction, is the weight factor of the jth transaction behavior feature item, is the characteristic value of the jth transaction behavior characteristic item, is the mean value of the j-th transaction behavior feature item, is the standard deviation of the j-th transaction behavior characteristic item, is an exponential function, is the total number of transaction behavior feature items.

5. The method for dynamic account attribute management based on business changes according to claim 4, characterized in that: The calculating of the cumulative risk coefficient of the i-th business transaction includes: Retrieve the transaction risk coefficient of each business transaction; The cumulative risk coefficient is calculated by formulating the transaction risk coefficient of each business transaction; the calculation formula is: ; Where: is the cumulative risk factor, The total number of business transactions.

6. The method for dynamic account attribute management based on business changes according to claim 5, characterized in that: The model expression of the pre-built credit assessment model is as follows: ； Where: To change your credit score, is the initial credit score, is the credit score correction factor, is a logarithmic function, is the inverse tangent function, and (a, b) is the preset risk coefficient interval.

7. The method for dynamic account attribute management based on business changes according to claim 6, characterized in that: The determining of the first target authority level to which the virtual account belongs when executing the i-th business transaction includes: Retrieving pre-stored credit score intervals; the credit score intervals include a first credit score interval, a second credit score interval, and a third credit score interval; The changed credit score is compared with the credit score interval, the credit score interval to which the changed credit score belongs is taken as the target credit score interval, and based on the mapping relationship between the credit score interval and the authority level, the first target authority level to which the virtual account belongs when executing the i-th business transaction is obtained.

8. The method for dynamic account attribute management based on business changes according to claim 7, characterized in that: The selecting a transaction for the i-th business transaction includes: Extract the amount range to which the transaction amount of the i-th business transaction belongs, and according to the preset relationship between the amount range and the authority level, use the authority level associated with the amount range as the second target authority level; Comparing the first target permission level with the second target permission level; If the first target permission level is higher than the second target permission level, or the first target permission level is the same as the second target permission level, the operation of the i-th business transaction is allowed to be performed; If the first target authority level is lower than the second target authority level, the operation of the i-th business transaction is prohibited.

9. A dynamic account attribute management system based on business changes, characterized in that: include: A data acquisition module is used to obtain the initial credit score of the virtual account, record the i-th business transaction of the virtual account, and collect transaction behavior feature data when the user operates the i-th business transaction through the virtual account, where i is an integer greater than zero; The risk regression module is used to input the transaction behavior feature data into the pre-trained transaction risk assessment model to obtain the transaction risk coefficient when the virtual account operates the i-th business transaction; A level determination module is used to calculate the cumulative risk coefficient of the i-th business transaction, input the cumulative risk coefficient, the initial credit score and the transaction risk coefficient into a pre-built credit assessment model to obtain the variable credit score of the virtual account, and determine the first target authority level of the virtual account when executing the i-th business transaction according to the variable credit score; The transaction selection module is used to select a transaction for the i-th business transaction according to the first target authority level of the virtual account at the current moment, and to assign and update the initial credit score according to the changed credit score; the transaction selection includes one of allowing execution or prohibiting execution.

Images